Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3430 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1157. Min Range: -2.1157

Max Act: 2.1157. Min Act: -0.0000

Data Index: 1588593 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.7884. Min Act: -0.0000

Data Index: 1407609 (Python Code)

Max Activating Token Index: 401

Text #2

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.6975. Min Act: -0.0000

Data Index: 1422849 (Python Code)

Max Activating Token Index: 230

Text #3

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.6984. Min Act: -0.0000

Data Index: 1364977 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1575901 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.4546. Min Act: -0.0000

Data Index: 1598398 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.3918. Min Act: -0.0000

Data Index: 1649136 (Python Code)

Max Activating Token Index: 824

Text #7

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1401690 (Python Code)

Max Activating Token Index: 545

Text #8

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.4641. Min Act: -0.0000

Data Index: 1553090 (Python Code)

Max Activating Token Index: 931

Text #9

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1509154 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1508100 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.2986. Min Act: -0.0000

Data Index: 1470819 (Python Code)

Max Activating Token Index: 275

Text #12

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1553557 (Python Code)

Max Activating Token Index: 724

Text #13

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1559666 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1562145 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1656515 (Python Code)

Max Activating Token Index: 375

Text #16

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1527152 (Python Code)

Max Activating Token Index: 492

Text #17

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1602843 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1486520 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 2.1157. Min Range: -2.1157

Max Act: 1.3342. Min Act: -0.0000

Data Index: 809708 (C4 (Web Text))

Max Activating Token Index: 915